Pratikakis, I.Savelonas, M.A.Arnaoutoglou, F.Ioannakis, G.Koutsoudis, A.Theoharis, T.Tran, M.-T.Nguyen, V.-T.Pham, V.-K.Nguyen, H.-D.Le, H.-A.Tran, B.-H.To, Q.H.Truong, M.-B.Phan, T.V.Nguyen, M.-D.Than, T.-A.Mac, K.-N.C.Do, M.N.Duong, A-D.Furuya, T.Ohbuchi, R.Aono, M.Tashiro, S.Pickup, D.Sun, X.Rosin, P.L.Martin, R.R.A. Ferreira and A. Giachetti and D. Giorgi2016-05-042016-05-042016978-3-03868-004-81997-0471https://doi.org/10.2312/3dor.20161091Despite numerous recent efforts, 3D object retrieval based on partial shape queries remains a challenging problem, far from being solved. The problem can be defined as: given a partial view of a shape as query, retrieve all partially similar 3D models from a repository. The objective of this track is to evaluate the performance of partial 3D object retrieval methods, for partial shape queries of various scan qualities and degrees of partiality. The retrieval problem is often found in cultural heritage applications, for which partial scans of objects query a dataset of geometrically distinct classes.H.3.2 [Information storage and retrieval]Information search and retrievalI.2.10 [Artificial Intelligence]Vision and Scene UnderstandingShape10.2312/3dor.2016109179-88